© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159654
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    win or lose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    गंध
    0.48
    спользова
    0.47
    }}}{\
    0.46
    睪
    0.46
    сте
    0.45
    ều
    0.45
     ле
    0.44
     पूंजी
    0.44
     चुंबकीय
    0.43
    }}[
    0.43
    POSITIVE LOGITS
    -
    0.48
    バイト
    0.46
    在這
    0.45
    ILL
    0.42
    在这
    0.42
    berts
    0.42
    un
    0.41
    かる
    0.41
    ba
    0.41
    のお
    0.41
    Activations Density 0.001%

    No Known Activations